Imperative to accelerate research aligning real-time clinical demand with mental health supply

The therapeutic effectiveness of artificial intelligence-based chatbots in alleviation of depressive and anxiety symptoms in short-course treatments: A systematic review and meta-analysis

BACKGROUND

The emergence of artificial intelligence-based chatbot has revolutionized the field of clinical psychology and psychotherapy, granting individuals unprecedented access to professional assistance, overcoming time constraints and geographical limitations with cost-effective convenience. However, despite its potential, there has been a noticeable gap in the literature regarding their effectiveness in addressing common mental health issues like depression and anxiety. This meta-analysis aims to evaluate the efficacy of AI-based chatbots in treating these conditions.

METHODS

A systematic search was executed across multiple databases, including PubMed, Cochrane Library, Web of Science, PsycINFO, and Embase on April 4th, 2024. The effect size of treatment efficacy was calculated using the standardized mean difference (Hedge's g). Quality assessment measures were implemented to ensure trial's quality.

RESULTS

In our analysis of 18 randomized controlled trials involving 3477 participants, we observed noteworthy improvements in depression (g = -0.26, 95 % CI = -0.34, -0.17) and anxiety (g = -0.19, 95 % CI = -0.29, -0.09) symptoms. The most significant benefits were evident after 8 weeks of treatment. However, at the three-month follow-up, no substantial effects were detected for either condition.

LIMITATIONS

Several limitations should be considered. These include the lack of diversity in the study populations, variations in chatbot design, and the use of different psychotherapeutic approaches. These factors may limit the generalizability of our findings.

CONCLUSION

This meta-analysis highlights the promising role of AI-based chatbot interventions in alleviating depressive and anxiety symptoms among adults. Our results indicate that these interventions can yield substantial improvements over a relatively brief treatment period.

Is cognitive behavioral therapy more effective than pharmacotherapy for binge spectrum disorders? A systematic review and meta-analysis

OBJECTIVES

Binge spectrum disorders are prevalent worldwide. Psychiatric and medical comorbidities are common, and societal costs are significant. Evidence-based treatment remains underutilized. Cognitive behavioral therapy is the recommended first-line treatment, but pharmacotherapy may be easier to access.

INTERVENTIONS

Meta-analytic evidence directly comparing cognitive behavioral therapy with pharmacotherapy is lacking. We aimed to compare the effects of cognitive behavioral therapy interventions with any pharmacological treatment for binge spectrum disorders. We searched PubMed, Embase, CENTRAL, ClinicalTrials.gov and reference lists for randomized controlled trials comparing cognitive behavioral therapy with any pharmacotherapy for bulimia nervosa/binge eating disorder and performed pairwise meta-analytic evaluations.

PRIMARY OUTCOMES

Primary outcomes are remission and frequency of binges. Secondary outcomes are frequency of purges, response, eating disorder psychopathology, weight/body mass index, depression, anxiety, quality of life and dropouts.

RESULTS

Eleven randomized controlled trials comparing cognitive behavioral therapy with fluoxetine/imipramine/desipramine/methylphenidate/sibutramine were identified (N = 531). Cognitive behavioral therapy was superior to antidepressants in terms of remission, frequency of binges and eating disorder psychopathology. There were no statistically significant differences for any of the individual cognitive behavioral therapy vs drug comparisons in terms of response/depression/anxiety/weight/quality of life/dropouts. Cognitive behavioral therapy was not superior to sibutramine/methylphenidate for the primary outcomes.

CONCLUSIONS

Data are scarce, comparisons underpowered and, considering the inherent methodological limitations of psychotherapy trials, questions arise regarding the presumed superiority of cognitive behavioral therapy. Further research is needed.

Self-harm by single- and multi-agent medication poisoning in a retrospective analysis of a Poison Control Center database from January 2018 to December 2022

PURPOSE

Medication poisoning is the most common method of self-harm. Longitudinal studies incorporating pre- and post-COVID-19 pandemic data are required to describe the phenomenon and to evaluate the long-term impact on mental health.

METHODS

Calls to the Poison Control Center of Policlinico Umberto I Hospital - Sapienza University of Rome, Italy, were analyzed retrospectively for characteristics and clinical presentation of cases of interest from January 2018 to December 2022.

RESULTS

A total of 756 cases of self-harm by medication poisonings were recorded in the study period. A reduction in rate of cases in 2020 was followed by a return to pre-pandemic levels by 2021. When separately analyzing single- and multi-agent cases, occurrence of cases involving just one medication increased since early 2021, with a peak in 2022 (7.8% of total calls, 95% CI 6.2-9.5, from 4.9%, 95% CI 4.1-5.8 in 2018). This increase in the rate of cases, mostly of none or mild severity, was driven by youth aged 12-21, in which the relative proportion of single- versus multi-agent cases showed an increasing trend since 2020 (from 42.6% in 2018 to 78.6% in 2022). Acetaminophen was the medication most frequently involved and benzodiazepines the largest class. A psychiatric background was increasingly seen in 2022, especially in age group 12-21.

CONCLUSION

Single-agent medication self-harm may be an increasingly prevailing phenomenon. Young adolescents with a psychiatric background might be most vulnerable to this behavior in the COVID-19 pandemic aftermath. Healthcare professionals should expect favorable clinical outcome and improve both counseling and psychotherapy supervision in individuals at risk.

The Appa Health App for Youth Mental Health: Development and Usability Study

BACKGROUND

Demand for adolescent mental health services has surged in the aftermath of the COVID-19 pandemic, and traditional models of care entailing in-person services with licensed mental health providers are inadequate to meet demand. However, research has shown that with proper training and supervision mentors can work with youth with mental health challenges like depression and anxiety and can even support the use of evidence-based strategies like cognitive behavioral therapy (CBT). In our increasingly connected world, youth mentors can meet with young people on a web-based platform at their convenience, reducing barriers to care. Moreover, the internet has made evidence-based CBT skills for addressing depression and anxiety more accessible than ever. As such, when trained and supervised by licensed clinicians, mentors are an untapped resource to support youth with mental health challenges.

OBJECTIVE

The objective of this study was to develop and assess the feasibility and acceptability of Appa Health (Appa), an evidence-based mental health mentoring program for youth experiencing symptoms of depression and anxiety. This paper describes the development, pilot testing process, and preliminary quantitative and qualitative outcomes of Appa's 12-week smartphone app program which combines web-based near-peer mentorship with short-form TikTok-style videos teaching CBT skills created by licensed mental health professionals who are also social media influencers.

METHODS

The development and testing processes were executed through collaboration with key stakeholders, including young people and clinical and research advisory boards. In the pilot study, young people were assessed for symptoms of depression or anxiety using standard self-report clinical measures: the Patient Health Questionnaire-8 and the Generalized Anxiety Disorder-7 scales. Teenagers endorsing symptoms of depression or anxiety (n=14) were paired with a mentor (n=10) based on preferred characteristics such as gender, race or ethnicity, and lesbian, gay, bisexual, transgender, queer (LGBTQ) status. Quantitative survey data about the teenagers' characteristics, mental health, and feasibility and acceptability were combined with qualitative data assessing youth perspectives on the program, their mentors, and the CBT content.

RESULTS

Participants reported finding Appa helpful, with 100% (n=14) of teenagers expressing that they felt better after the 12-week program. Over 85% (n=12) said they would strongly recommend the program to a friend. The teenagers were engaged, video chatting with mentors consistently over the 12 weeks. Metrics of anxiety and depressive symptoms reduced consistently from week 1 to week 12, supporting qualitative data suggesting that mentoring combined with CBT strategies has the potential to positively impact youth mental health and warrants further study.

CONCLUSIONS

Appa Health is a novel smartphone app aiming to improve the well-being of youth and reduce anxiety and depressive symptoms through web-based mentoring and engaging CBT video content. This formative research sets the stage for a large-scale randomized controlled trial recently funded by the National Institutes of Health Small Business Innovation Research program.

Providing Self-Led Mental Health Support Through an Artificial Intelligence-Powered Chat Bot (Leora) to Meet the Demand of Mental Health Care

Digital mental health services are becoming increasingly valuable for addressing the global public health burden of mental ill-health. There is significant demand for scalable and effective web-based mental health services. Artificial intelligence (AI) has the potential to improve mental health through the deployment of chatbots. These chatbots can provide round-the-clock support and triage individuals who are reluctant to access traditional health care due to stigma. The aim of this viewpoint paper is to consider the feasibility of AI-powered platforms to support mental well-being. The Leora model is considered a model with the potential to provide mental health support. Leora is a conversational agent that uses AI to engage in conversations with users about their mental health and provide support for minimal-to-mild symptoms of anxiety and depression. The tool is designed to be accessible, personalized, and discreet, offering strategies for promoting well-being and acting as a web-based self-care coach. Across all AI-powered mental health services, there are several challenges in the ethical development and deployment of AI in mental health treatment, including trust and transparency, bias and health inequity, and the potential for negative consequences. To ensure the effective and ethical use of AI in mental health care, researchers must carefully consider these challenges and engage with key stakeholders to provide high-quality mental health support. Validation of the Leora platform through rigorous user testing will be the next step in ensuring the model is effective.